# KeyVideoLLM: Towards Large-scale Video Keyframe Selection

arXiv: https://arxiv.org/abs/2407.03104 · HTML: https://mlsanity.com/paper/2407.03104/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2311.13165/) (2023)
- [X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval](https://mlsanity.com/paper/2203.15086/) (2022)
- [BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions](https://mlsanity.com/paper/2308.09936/) (2023)
- [MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens](https://mlsanity.com/paper/2404.03413/) (2024)
- [MoDS: Model-oriented Data Selection for Instruction Tuning](https://mlsanity.com/paper/2311.15653/) (2023)
- [VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding](https://mlsanity.com/paper/2105.09996/) (2021)
- [Video Summarization Using Deep Neural Networks: A Survey](https://mlsanity.com/paper/2101.06072/) (2021)
- [A Survey of Multimodal Large Language Model from A Data-centric Perspective](https://mlsanity.com/paper/2405.16640/) (2024)
- [Koala: Key frame-conditioned long video-LLM](https://mlsanity.com/paper/2404.04346/) (2024)
- [FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement](https://mlsanity.com/paper/2304.03946/) (2023)
- [Rethinking the Instruction Quality: LIFT is What You Need](https://mlsanity.com/paper/2312.11508/) (2023)
- [Semantically consistent Video-to-Audio Generation using Multimodal Language Large Model](https://mlsanity.com/paper/2404.16305/) (2024)
- [From BERT to GPT-3 Codex: Harnessing the Potential of Very Large Language Models for Data Management](https://mlsanity.com/paper/2306.09339/) (2023)
- [Lingua Manga: A Generic Large Language Model Centric System for Data Curation](https://mlsanity.com/paper/2306.11702/) (2023)

## Built on by (most cited first, 30 of 54)

- [Frame-Voyager: Learning to Query Frames for Video Large Language Models](https://mlsanity.com/paper/2410.03226/) (2024)
- [Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs](https://mlsanity.com/paper/2506.22139/) (2025)
- [MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs](https://mlsanity.com/paper/2501.02885/) (2025)
- [FOCUS: Efficient Keyframe Selection for Long Video Understanding](https://mlsanity.com/paper/2510.27280/) (2025)
- [Improving LLM Video Understanding with 16 Frames Per Second](https://mlsanity.com/paper/2503.13956/) (2025)
- [Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs](https://mlsanity.com/paper/2506.07180/) (2025)
- [TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning](https://mlsanity.com/paper/2511.05489/) (2025)
- [Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing](https://mlsanity.com/paper/2503.10742/) (2025)
- [REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding](https://mlsanity.com/paper/2511.13026/) (2025)
- [Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior](https://mlsanity.com/paper/2512.06866/) (2025)
- [ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning](https://mlsanity.com/paper/2505.15447/) (2025)
- [Position: Foundation Models Need Digital Twin Representations](https://mlsanity.com/paper/2505.03798/) (2025)
- [AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding](https://mlsanity.com/paper/2510.02778/) (2025)
- [Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects](https://mlsanity.com/paper/2604.05546/) (2026)
- [ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning](https://mlsanity.com/paper/2603.28610/) (2026)
- [FrameOracle: Learning What to See and How Much to See in Videos](https://mlsanity.com/paper/2510.03584/) (2025)
- [AdaCodec: A Predictive Visual Code for Video MLLMs](https://mlsanity.com/paper/2606.02569/) (2026)
- [BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models](https://mlsanity.com/paper/2410.09804/) (2024)
- [Language-Guided Temporal Token Pruning for Efficient VideoLLM Processing](https://mlsanity.com/paper/2508.17686/) (2025)
- [GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory](https://mlsanity.com/paper/2511.12027/) (2025)
- [ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning](https://mlsanity.com/paper/2512.02835/) (2025)
- [OpenWorldLib: A Unified Codebase and Definition of Advanced World Models](https://mlsanity.com/paper/2604.04707/) (2026)
- [TriPSS: A Tri-Modal Keyframe Extraction Framework Using Perceptual, Structural, and Semantic Representations](https://mlsanity.com/paper/2506.05395/) (2025)
- [Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories](https://mlsanity.com/paper/2509.16176/) (2025)
- [ViSIL: Unified Evaluation of Information Loss in Multimodal Video Captioning](https://mlsanity.com/paper/2601.09851/) (2026)
- [Understanding Multimodal Complementarity for Single-Frame Action Anticipation](https://mlsanity.com/paper/2601.22039/) (2026)
- [TiFRe: Text-guided Video Frame Reduction for Efficient Video Multi-modal Large Language Models](https://mlsanity.com/paper/2602.08861/) (2026)
- [AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding](https://mlsanity.com/paper/2603.28696/) (2026)
- [LDDR: Linear-DPP-Based Dynamic-Resolution Frame Sampling for Video MLLMs](https://mlsanity.com/paper/2605.11477/) (2026)
- [PEEK: Picking Essential frames via Efficient Knowledge distillation](https://mlsanity.com/paper/2605.31029/) (2026)

## Abstract (arXiv)

Recently, with the rise of web videos, managing and understanding large-scale video datasets has become increasingly important. Video Large Language Models (VideoLLMs) have emerged in recent years due to their strong video understanding capabilities. However, training and inference processes for VideoLLMs demand vast amounts of data, presenting significant challenges to data management, particularly regarding efficiency, robustness, and effectiveness. In this work, we present KeyVideoLLM, a text-video frame similarity-based keyframe selection method designed to manage VideoLLM data efficiently, robustly, and effectively. Specifically, KeyVideoLLM achieves a remarkable data compression rate of up to 60.9 times, substantially lowering disk space requirements, which proves its high efficiency. Additionally, it maintains a 100% selection success rate across all video formats and scales, enhances processing speed by up to 200 times compared to existing keyframe selection methods, and does not require hyperparameter tuning. Beyond its outstanding efficiency and robustness, KeyVideoLLM further improves model performance in video question-answering tasks during both training and inference stages. Notably, it consistently achieved the state-of-the-art (SoTA) experimental results on diverse datasets.